6 files changed, 95 insertions, 50 deletions

diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 356970f3b..95a000515 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -46,4 +46,6 @@ config KVM_ARM_HOST
 	---help---
 	  Provides host support for ARM processors.
 
+source drivers/vhost/Kconfig
+
 endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 78b286994..e06fd299d 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -271,6 +271,16 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvm_timer_should_fire(vcpu);
 }
 
+void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
+{
+	kvm_timer_schedule(vcpu);
+}
+
+void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+	kvm_timer_unschedule(vcpu);
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	/* Force users to call KVM_ARM_VCPU_INIT */
@@ -308,7 +318,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	if (vcpu->arch.pause)
+	if (vcpu->arch.power_off)
 		mp_state->mp_state = KVM_MP_STATE_STOPPED;
 	else
 		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
@@ -321,10 +331,10 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 {
 	switch (mp_state->mp_state) {
 	case KVM_MP_STATE_RUNNABLE:
-		vcpu->arch.pause = false;
+		vcpu->arch.power_off = false;
 		break;
 	case KVM_MP_STATE_STOPPED:
-		vcpu->arch.pause = true;
+		vcpu->arch.power_off = true;
 		break;
 	default:
 		return -EINVAL;
@@ -342,7 +352,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
  */
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v);
+	return ((!!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v))
+		&& !v->arch.power_off && !v->arch.pause);
 }
 
 /* Just ensure a guest exit from a particular CPU */
@@ -468,11 +479,38 @@ bool kvm_arch_intc_initialized(struct kvm *kvm)
 	return vgic_initialized(kvm);
 }
 
-static void vcpu_pause(struct kvm_vcpu *vcpu)
+static void kvm_arm_halt_guest(struct kvm *kvm) __maybe_unused;
+static void kvm_arm_resume_guest(struct kvm *kvm) __maybe_unused;
+
+static void kvm_arm_halt_guest(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		vcpu->arch.pause = true;
+	force_vm_exit(cpu_all_mask);
+}
+
+static void kvm_arm_resume_guest(struct kvm *kvm)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+
+		vcpu->arch.pause = false;
+		wake_up_interruptible(wq);
+	}
+}
+
+static void vcpu_sleep(struct kvm_vcpu *vcpu)
 {
 	wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
 
-	wait_event_interruptible(*wq, !vcpu->arch.pause);
+	wait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+				       (!vcpu->arch.pause)));
 }
 
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
@@ -522,14 +560,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		update_vttbr(vcpu->kvm);
 
-		if (vcpu->arch.pause)
-			vcpu_pause(vcpu);
-
-		/*
-		 * Disarming the background timer must be done in a
-		 * preemptible context, as this call may sleep.
-		 */
-		kvm_timer_flush_hwstate(vcpu);
+		if (vcpu->arch.power_off || vcpu->arch.pause)
+			vcpu_sleep(vcpu);
 
 		/*
 		 * Preparing the interrupts to be injected also
@@ -537,6 +569,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
 		local_irq_disable();
@@ -549,11 +582,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			run->exit_reason = KVM_EXIT_INTR;
 		}
 
-		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
+		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
+			vcpu->arch.power_off || vcpu->arch.pause) {
 			local_irq_enable();
+			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			preempt_enable();
-			kvm_timer_sync_hwstate(vcpu);
 			continue;
 		}
 
@@ -596,14 +630,19 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * guest time.
 		 */
 		kvm_guest_exit();
-		trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+
+		/*
+		 * We must sync the timer state before the vgic state so that
+		 * the vgic can properly sample the updated state of the
+		 * interrupt line.
+		 */
+		kvm_timer_sync_hwstate(vcpu);
 
 		kvm_vgic_sync_hwstate(vcpu);
 
 		preempt_enable();
 
-		kvm_timer_sync_hwstate(vcpu);
-
 		ret = handle_exit(vcpu, run, ret);
 	}
 
@@ -765,12 +804,12 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 	vcpu_reset_hcr(vcpu);
 
 	/*
-	 * Handle the "start in power-off" case by marking the VCPU as paused.
+	 * Handle the "start in power-off" case.
 	 */
 	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
-		vcpu->arch.pause = true;
+		vcpu->arch.power_off = true;
 	else
-		vcpu->arch.pause = false;
+		vcpu->arch.power_off = false;
 
 	return 0;
 }
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 974b1c606..3a10c9f1d 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -115,7 +115,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
 			       data);
 		data = vcpu_data_host_to_guest(vcpu, data, len);
-		*vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data;
+		vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
 	}
 
 	return 0;
@@ -186,7 +186,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	rt = vcpu->arch.mmio_decode.rt;
 
 	if (is_write) {
-		data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len);
+		data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt),
+					       len);
 
 		trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data);
 		mmio_write_buf(data_buf, len, data);
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 6984342da..61d96a645 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -98,6 +98,11 @@ static void kvm_flush_dcache_pud(pud_t pud)
 	__kvm_flush_dcache_pud(pud);
 }
 
+static bool kvm_is_device_pfn(unsigned long pfn)
+{
+	return !pfn_valid(pfn);
+}
+
 /**
  * stage2_dissolve_pmd() - clear and flush huge PMD entry
  * @kvm:	pointer to kvm structure.
@@ -213,7 +218,7 @@ static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
 			kvm_tlb_flush_vmid_ipa(kvm, addr);
 
 			/* No need to invalidate the cache for device mappings */
-			if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
 				kvm_flush_dcache_pte(old_pte);
 
 			put_page(virt_to_page(pte));
@@ -305,8 +310,7 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		if (!pte_none(*pte) &&
-		    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+		if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte)))
 			kvm_flush_dcache_pte(*pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
@@ -1037,11 +1041,6 @@ static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_dabt_iswrite(vcpu);
 }
 
-static bool kvm_is_device_pfn(unsigned long pfn)
-{
-	return !pfn_valid(pfn);
-}
-
 /**
  * stage2_wp_ptes - write protect PMD range
  * @pmd:	pointer to pmd entry
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index ad6f6424f..a9b3b905e 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -63,7 +63,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu)
 
 static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.pause = true;
+	vcpu->arch.power_off = true;
 }
 
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
@@ -75,7 +75,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	unsigned long context_id;
 	phys_addr_t target_pc;
 
-	cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+	cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
@@ -87,15 +87,15 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 */
 	if (!vcpu)
 		return PSCI_RET_INVALID_PARAMS;
-	if (!vcpu->arch.pause) {
+	if (!vcpu->arch.power_off) {
 		if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
 			return PSCI_RET_ALREADY_ON;
 		else
 			return PSCI_RET_INVALID_PARAMS;
 	}
 
-	target_pc = *vcpu_reg(source_vcpu, 2);
-	context_id = *vcpu_reg(source_vcpu, 3);
+	target_pc = vcpu_get_reg(source_vcpu, 2);
+	context_id = vcpu_get_reg(source_vcpu, 3);
 
 	kvm_reset_vcpu(vcpu);
 
@@ -114,8 +114,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
 	 * the general puspose registers are undefined upon CPU_ON.
 	 */
-	*vcpu_reg(vcpu, 0) = context_id;
-	vcpu->arch.pause = false;
+	vcpu_set_reg(vcpu, 0, context_id);
+	vcpu->arch.power_off = false;
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
@@ -134,8 +134,8 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu *tmp;
 
-	target_affinity = *vcpu_reg(vcpu, 1);
-	lowest_affinity_level = *vcpu_reg(vcpu, 2);
+	target_affinity = vcpu_get_reg(vcpu, 1);
+	lowest_affinity_level = vcpu_get_reg(vcpu, 2);
 
 	/* Determine target affinity mask */
 	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
@@ -153,7 +153,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 		mpidr = kvm_vcpu_get_mpidr_aff(tmp);
 		if ((mpidr & target_affinity_mask) == target_affinity) {
 			matching_cpus++;
-			if (!tmp->arch.pause)
+			if (!tmp->arch.power_off)
 				return PSCI_0_2_AFFINITY_LEVEL_ON;
 		}
 	}
@@ -179,7 +179,7 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type)
 	 * re-initialized.
 	 */
 	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
-		tmp->arch.pause = true;
+		tmp->arch.power_off = true;
 		kvm_vcpu_kick(tmp);
 	}
 
@@ -209,7 +209,7 @@ int kvm_psci_version(struct kvm_vcpu *vcpu)
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
 	int ret = 1;
-	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
 
 	switch (psci_fn) {
@@ -273,13 +273,13 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	*vcpu_reg(vcpu, 0) = val;
+	vcpu_set_reg(vcpu, 0, val);
 	return ret;
 }
 
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
-	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
 
 	switch (psci_fn) {
@@ -295,7 +295,7 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	*vcpu_reg(vcpu, 0) = val;
+	vcpu_set_reg(vcpu, 0, val);
 	return 1;
 }
 
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index 0ec35392d..c25a88598 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -25,21 +25,25 @@ TRACE_EVENT(kvm_entry,
 );
 
 TRACE_EVENT(kvm_exit,
-	TP_PROTO(unsigned int exit_reason, unsigned long vcpu_pc),
-	TP_ARGS(exit_reason, vcpu_pc),
+	TP_PROTO(int idx, unsigned int exit_reason, unsigned long vcpu_pc),
+	TP_ARGS(idx, exit_reason, vcpu_pc),
 
 	TP_STRUCT__entry(
+		__field(	int,		idx		)
 		__field(	unsigned int,	exit_reason	)
 		__field(	unsigned long,	vcpu_pc		)
 	),
 
 	TP_fast_assign(
+		__entry->idx			= idx;
 		__entry->exit_reason		= exit_reason;
 		__entry->vcpu_pc		= vcpu_pc;
 	),
 
-	TP_printk("HSR_EC: 0x%04x, PC: 0x%08lx",
+	TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+		  __print_symbolic(__entry->idx, kvm_arm_exception_type),
 		  __entry->exit_reason,
+		  __print_symbolic(__entry->exit_reason, kvm_arm_exception_class),
 		  __entry->vcpu_pc)
 );